[clang] 9f0f606 - [clang] Provide an SSE4.2 implementation of identifier token lexer (#68962)

[via cfe-commits]

Author: serge-sans-paille
Date: 2023-10-19T08:45:54Z
New Revision: 9f0f6060810ebd3006f62149d4739fc54af68536

URL: https://github.com/llvm/llvm-project/commit/9f0f6060810ebd3006f62149d4739fc54af68536
DIFF: https://github.com/llvm/llvm-project/commit/9f0f6060810ebd3006f62149d4739fc54af68536.diff

LOG: [clang] Provide an SSE4.2 implementation of identifier token lexer (#68962)

The _mm_cmpistri instruction can be used to quickly parse identifiers.

With this patch activated, clang pre-processes <iostream> 1.8% faster,
and sqlite3.c amalgametion 1.5% faster, based on time measurements and
number of executed instructions as measured by valgrind.

The introduction of an extra helper function in the regular case has no
impact on performance, see


https://llvm-compile-time-tracker.com/compare.php?from=30240e428f0ec7d4a6d1b84f9f807ce12b46cfd1&to=12bcb016cde4579ca7b75397762098c03eb4f264&stat=instructions:u

---------

Co-authored-by: serge-sans-paille <sguelton at mozilla.com>

Added: 
    

Modified: 
    clang/lib/Lex/Lexer.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp
index feed1b9ecd71a8d..675ec28e514797e 100644
--- a/clang/lib/Lex/Lexer.cpp
+++ b/clang/lib/Lex/Lexer.cpp
@@ -47,6 +47,10 @@
 #include <tuple>
 #include <utility>
 
+#ifdef __SSE4_2__
+#include <nmmintrin.h>
+#endif
+
 using namespace clang;
 
 //===----------------------------------------------------------------------===//
@@ -1847,19 +1851,47 @@ bool Lexer::LexUnicodeIdentifierStart(Token &Result, uint32_t C,
   return true;
 }
 
+static const char *
+fastParseASCIIIdentifier(const char *CurPtr,
+                         [[maybe_unused]] const char *BufferEnd) {
+#ifdef __SSE4_2__
+  alignas(16) static constexpr char AsciiIdentifierRange[16] = {
+      '_', '_', 'A', 'Z', 'a', 'z', '0', '9',
+  };
+  constexpr ssize_t BytesPerRegister = 16;
+
+  __m128i AsciiIdentifierRangeV =
+      _mm_load_si128((const __m128i *)AsciiIdentifierRange);
+
+  while (LLVM_LIKELY(BufferEnd - CurPtr >= BytesPerRegister)) {
+    __m128i Cv = _mm_loadu_si128((const __m128i *)(CurPtr));
+
+    int Consumed = _mm_cmpistri(AsciiIdentifierRangeV, Cv,
+                                _SIDD_LEAST_SIGNIFICANT | _SIDD_CMP_RANGES |
+                                    _SIDD_UBYTE_OPS | _SIDD_NEGATIVE_POLARITY);
+    CurPtr += Consumed;
+    if (Consumed == BytesPerRegister)
+      continue;
+    return CurPtr;
+  }
+#endif
+
+  unsigned char C = *CurPtr;
+  while (isAsciiIdentifierContinue(C))
+    C = *++CurPtr;
+  return CurPtr;
+}
+
 bool Lexer::LexIdentifierContinue(Token &Result, const char *CurPtr) {
   // Match [_A-Za-z0-9]*, we have already matched an identifier start.
+
   while (true) {
-    unsigned char C = *CurPtr;
-    // Fast path.
-    if (isAsciiIdentifierContinue(C)) {
-      ++CurPtr;
-      continue;
-    }
+
+    CurPtr = fastParseASCIIIdentifier(CurPtr, BufferEnd);
 
     unsigned Size;
     // Slow path: handle trigraph, unicode codepoints, UCNs.
-    C = getCharAndSize(CurPtr, Size);
+    unsigned char C = getCharAndSize(CurPtr, Size);
     if (isAsciiIdentifierContinue(C)) {
       CurPtr = ConsumeChar(CurPtr, Size, Result);
       continue;